Automatic control system for garbage classification treatment

Abstract

The invention discloses an automatic control system for garbage classification treatment, the automatic control system comprises an identity acquisition module, a garbage sensing module, an image acquisition module, a first analysis module, a vibration module and a second analysis module, the identity acquisition module is used for acquiring and verifying identity information of a user; the first analysis module is used for identifying the identity information of the user, starting the garbage sensing module after the identity information of the user passes the verification, enabling the image acquisition module to acquire a top view image of the to-be-classified garbage at the moment as a first image when the garbage sensing module senses the to-be-classified garbage, and analyzing the first image by the first analysis module; whether the to-be-classified garbage is suspected mixed garbage or not is judged, and after the first analysis module judges that the to-be-classified garbage is suspected mixed garbage, the vibration module is made to vibrate the to-be-classified garbage.

Description

Technical Field

[0001] The present invention relates to the technical field of control systems, and in particular to an automatic control system for garbage classification and processing. Background Art

[0002] Garbage classification refers to the storage, placement and transportation of garbage according to certain regulations or standards. The purpose of garbage classification is to improve the resource value and economic value of garbage, strive to make the best use of materials, reduce the amount of garbage processed and the use of processing equipment, reduce processing costs, and reduce the consumption of land resources.

[0003] Sorting garbage can not only improve the recycling rate of certain resources, but also reduce the pressure on the ecological environment. Garbage sorting is imminent.

[0004] However, at present, there are some unethical people who do not sort the garbage when putting it into the trash bin, but mix the garbage together. Summary of the invention

[0005] The object of the present invention is to provide an automatic control system for garbage classification processing to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an automatic control system for garbage classification and processing, the automatic control system comprising an identity collection module, a garbage sensing module, an image collection module, a first analysis module, a vibration module, a second analysis module and a garbage return control module, the identity collection module is used to collect and verify the identity information of the user, and after the user's identity information is verified, the garbage sensing module is turned on, when the garbage sensing module senses the garbage to be classified, the image collection module is ordered to collect the top view image of the garbage to be classified at this time as a first image, the first analysis module analyzes the first image to determine whether the garbage to be classified is suspected mixed garbage, after the first analysis module determines that the garbage to be classified is suspected mixed garbage, the vibration module is ordered to vibrate the garbage to be classified, and after the vibration, the image collection module is ordered to collect the top view image of the garbage to be classified at this time as a second image, the second analysis module compares the first image and the second image to determine whether the garbage to be classified is mixed garbage, and the garbage return control module is used to control the garbage to be returned to the user when it is determined that the garbage to be classified is mixed garbage.

[0007] Furthermore, the first analysis module includes a first similarity comparison module, a first contour extraction module, a sub-image division module and a second similarity comparison module, wherein the first similarity comparison module compares the first image with an image in a preset garbage database, wherein the garbage database is used to pre-store image information of various garbage, and there is image information of a certain garbage in the garbage database whose similarity with the first image is greater than a first similarity threshold, and the image information of the garbage is assumed to be the reference image information, the first contour extraction module is used to extract the contour of the garbage to be classified in the first image as the first contour, the sub-image division module determines the position of each quarter-division point on the first contour according to the length of the first contour, connects the center point of the garbage to be classified with each quarter-division point on the contour, and divides the garbage to be classified into four sub-images, the second similarity comparison module compares the four sub-images with the local image information in the reference image information, and if there is a sub-image whose similarity with the local image information in the reference image information is less than the second similarity threshold, the garbage to be classified is judged to be suspected mixed garbage.

[0008] Furthermore, the second analysis module includes a second contour extraction module, a length reference calculation module, a length reference comparison module, an inner diameter extraction module, a to-be-compared image acquisition module, a comparison image acquisition module and a third similarity comparison module. The second contour extraction module extracts the contour of the garbage to be classified in the second image as the second contour. The length reference calculation module calculates the length reference P=|L2-L1| / L1, wherein L1 is the length of the first contour and L2 is the length of the second contour. The length reference comparison module compares the length reference with a length reference threshold. When the length reference is greater than or equal to the length reference threshold, it is determined that the garbage to be classified is mixed garbage. When the length reference value is less than the length reference value threshold, the inner diameter extraction module extracts the maximum inner diameter and the minimum inner diameter of the first contour line and the second contour line respectively, the image to be compared acquisition module is used to obtain the four images to be compared that are divided within the first contour line by the maximum inner diameter and the minimum inner diameter of the first contour line, the comparison image acquisition module is used to obtain the four comparison images that are divided within the second contour line by the maximum inner diameter and the minimum inner diameter of the second contour line, the third similarity comparison module compares the comparison image with the image to be compared, and when there is a comparison image whose similarity with the four images to be compared is less than the third similarity threshold, it is determined that the garbage to be classified is mixed garbage.

[0009] Furthermore, the automatic control system also includes a weight acquisition module and a weight comparison module. The weight acquisition module is used to collect the weight of the garbage to be classified before and after vibration. The weight comparison module compares the weight of the garbage to be classified before and after vibration. When the difference in weight before and after vibration of the garbage to be classified is greater than or equal to a weight difference threshold, the garbage to be classified is judged to be mixed garbage. When the difference in weight before and after vibration of the garbage to be classified is less than the weight difference threshold, the image acquisition module is used to collect a top-down image of the garbage to be classified after vibration as the second image.

[0010] Furthermore, the automatic control system also includes an automatic control method, and the automatic control method includes the following steps: When the garbage sensor senses the garbage to be classified, a bird's-eye view image of the garbage to be classified is collected as a first image, and the first image is analyzed to determine whether the garbage to be classified is suspected mixed garbage. If the garbage to be classified is suspected to be mixed garbage, the top view image of the garbage to be classified is collected after vibrating the garbage to be classified as the second image. Compare the first image with the second image to determine whether the garbage to be classified is mixed garbage. If the garbage to be sorted is determined to be mixed garbage, the garbage to be sorted will be returned.

[0011] Further, the analyzing the first image includes: The first image is compared with an image in a preset garbage database, wherein the garbage database is used to pre-store image information of various garbage. If the similarity between the image information of a certain garbage in the garbage database and the first image is greater than a first similarity threshold, the image information of the garbage is set as the reference image information; Extracting the contour line of the garbage to be classified in the first image as the first contour line, determining the positions of the four-division points on the first contour line according to the length of the first contour line, connecting the center point of the garbage to be classified with the four-division points on the contour line respectively, and dividing the garbage to be classified into four sub-images; The four sub-images are compared with the local image information in the reference image information respectively. If the similarity between a certain sub-image and the local image information in the reference image information is less than a second similarity threshold, the garbage to be classified is determined to be suspected mixed garbage.

[0012] Furthermore, comparing the first image and the second image includes: The contour line of the garbage to be classified in the second image is extracted as the second contour line, and the length reference value P=|L2-L1| / L1 is calculated, where L1 is the length of the first contour line, and L2 is the length of the second contour line. If the length reference is greater than or equal to the length reference threshold, it is determined that the garbage to be classified is mixed garbage; If the length reference is less than the length reference threshold, the maximum inner diameter and the minimum inner diameter of the first contour line and the second contour line are extracted respectively, the maximum inner diameter and the minimum inner diameter of the first contour line divide the interior of the first contour line into four images to be compared within the first contour line, and the maximum inner diameter and the minimum inner diameter of the second contour line divide the interior of the second contour line into four comparison images within the second contour line. If there is a certain comparison image whose similarity with the four images to be compared is less than the third similarity threshold, then it is determined that the garbage to be classified is mixed garbage.

[0013] Furthermore, before collecting the overhead image of the garbage to be classified as the second image, the process further includes: The weight of the garbage to be sorted after vibration is collected, and compared with the weight of the garbage to be sorted before vibration. If the difference in weight before and after vibration of the garbage to be sorted is greater than or equal to a weight difference threshold, then the garbage to be sorted is judged to be mixed garbage. Otherwise, a top-view image of the garbage to be sorted is collected as the second image.

[0014] Furthermore, before the garbage sensor senses the garbage to be classified, the process further includes: Collect the user's identity information and turn on the spam sensor when the user's identity verification is passed.

[0015] Compared with the prior art, the beneficial effect achieved by the present invention is as follows: the present invention first compares the image information of the garbage to be classified with the image information in a preset garbage image database, and when it is determined that the garbage to be classified may be a mixture of different types of garbage, the garbage to be classified is vibrated, and the images of the garbage to be classified before and after the vibration are compared, so as to further determine whether the garbage to be classified is mixed garbage. After it is determined to be mixed garbage, the garbage to be classified is returned to the user for reclassification, and there is no need for human supervision to determine whether the user has classified the garbage before disposing of it. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a structural schematic diagram of the automatic control system for garbage disposal classification of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] See also Figure 1 , the present invention provides a technical solution: An automatic control system for garbage classification and processing, the automatic control system comprises an identity collection module, a garbage sensing module, an image collection module, a first analysis module, a vibration module, a second analysis module and a garbage return control module, the identity collection module is used to collect and verify the identity information of a user, and after the user's identity information is verified, the garbage sensing module is turned on, when the garbage sensing module senses the garbage to be classified, the image collection module is ordered to collect a top view image of the garbage to be classified at this time as a first image, the first analysis module analyzes the first image to determine whether the garbage to be classified is suspected mixed garbage, after the first analysis module determines that the garbage to be classified is suspected mixed garbage, the vibration module is ordered to vibrate the garbage to be classified, and after the vibration, the image collection module is ordered to collect a top view image of the garbage to be classified at this time as a second image, the second analysis module compares the first image and the second image to determine whether the garbage to be classified is mixed garbage, and the garbage return control module is used to control the garbage to be returned to the user when the garbage to be classified is determined to be mixed garbage.

[0019] The first analysis module includes a first similarity comparison module, a first contour extraction module, a sub-image division module and a second similarity comparison module. The first similarity comparison module compares the first image with an image in a preset garbage database, wherein the garbage database is used to pre-store image information of various garbage. In the garbage database, there is image information of a certain garbage whose similarity with the first image is greater than a first similarity threshold. The image information of the garbage is assumed to be reference image information. The first contour extraction module is used to extract the contour of the garbage to be classified in the first image as the first contour. The sub-image division module determines the positions of each quarter-divided point on the first contour according to the length of the first contour, connects the center point of the garbage to be classified with each quarter-divided point on the contour, and divides the garbage to be classified into four sub-images. The second similarity comparison module compares the four sub-images with the local image information in the reference image information respectively. If there is a sub-image whose similarity with the local image information in the reference image information is less than the second similarity threshold, the garbage to be classified is judged to be suspected mixed garbage.

[0020] The second analysis module includes a second contour extraction module, a length reference calculation module, a length reference comparison module, an inner diameter extraction module, a to-be-compared image acquisition module, a comparison image acquisition module and a third similarity comparison module. The second contour extraction module extracts the contour of the garbage to be classified in the second image as the second contour. The length reference calculation module calculates the length reference P=|L2-L1| / L1, where L1 is the length of the first contour and L2 is the length of the second contour. The length reference comparison module compares the length reference with a length reference threshold. If the length reference is greater than or equal to the length reference threshold, it is determined that the garbage to be classified is mixed garbage. If the length reference is greater than or equal to the length reference threshold, it is determined that the garbage to be classified is mixed garbage. When the value is less than the length reference threshold, the inner diameter extraction module extracts the maximum inner diameter and the minimum inner diameter of the first contour line and the second contour line respectively, the image to be compared acquisition module is used to obtain the four images to be compared that are divided within the first contour line by the maximum inner diameter and the minimum inner diameter of the first contour line, the comparison image acquisition module is used to obtain the four comparison images that are divided within the second contour line by the maximum inner diameter and the minimum inner diameter of the second contour line, the third similarity comparison module compares the comparison image with the image to be compared, and when there is a comparison image with the four images to be compared whose similarity is less than the third similarity threshold, it is determined that the garbage to be classified is mixed garbage.

[0021] The automatic control system also includes a weight acquisition module and a weight comparison module. The weight acquisition module is used to collect the weight of the garbage to be classified before and after vibration. The weight comparison module compares the weight of the garbage to be classified before and after vibration. When the difference in weight of the garbage to be classified before and after vibration is greater than or equal to a weight difference threshold, the garbage to be classified is judged to be mixed garbage. When the difference in weight of the garbage to be classified before and after vibration is less than the weight difference threshold, the image acquisition module is used to collect a top-view image of the garbage to be classified after vibration as the second image.

[0022] The automatic control system also includes an automatic control method, which includes the following steps: When the user's identity information is collected and verified, the garbage sensor is turned on. When the garbage sensor senses the garbage to be classified, a top view image of the garbage to be classified is collected as a first image, and the first image is analyzed to determine whether the garbage to be classified is suspected mixed garbage. The user's identity needs to be collected and verified in advance in this application because when the garbage to be classified is judged to be mixed garbage, that is, when it is judged that the garbage to be classified is composed of different types of garbage, the garbage to be classified needs to be returned, so that the user can classify the garbage to be classified and put it again, so as to facilitate the supervision of the user's garbage classification; If the garbage to be classified is suspected mixed garbage, the top view image of the garbage to be classified is collected after vibrating the garbage to be classified as the second image. The purpose of vibrating the garbage to be classified is, on the one hand, to determine whether there is liquid in the garbage to be classified. In garbage classification, the liquid should be poured into the sewer, so it is also necessary to determine whether there is liquid in the garbage to be classified. On the other hand, it is to determine whether the garbage to be classified is mixed garbage by collecting the garbage to be classified after vibration. The garbage sensor in this embodiment can be a light sensor. In order to further improve the accuracy of the detection image, the garbage to be classified can be vibrated before collecting the first image. Of course, this vibration is different from the vibration for judging that the garbage to be classified is suspected mixed garbage. This vibration is performed after the weight of the garbage to be classified is detected, so as to prevent the collected images from being images of different angles of the garbage to be classified due to subsequent vibration. Compare the first image with the second image to determine whether the garbage to be classified is mixed garbage. If the garbage to be sorted is determined to be mixed garbage, the garbage to be sorted will be returned and the user will be asked to separate the garbage to be sorted.

[0023] The analyzing the first image comprises: Comparing the first image with an image in a preset garbage database, wherein the garbage database is used to pre-store image information of various types of garbage, and each type of garbage is correspondingly stored with a garbage classification type; If the image information of a piece of garbage in the garbage database has a similarity with the first image greater than a first similarity threshold, the image information of the garbage is set as the reference image information; or the image information of the garbage in the garbage database corresponding to the maximum similarity with the first image is directly selected as the reference image information; Extracting the contour line of the garbage to be classified in the first image as the first contour line, determining the positions of the four-division points on the first contour line according to the length of the first contour line, connecting the center point of the garbage to be classified with the four-division points on the contour line respectively, and dividing the garbage to be classified into four sub-images; The four sub-images are compared with the local image information in the reference image information respectively. If there is a sub-image with a similarity less than the second similarity threshold between the local image information and the reference image information, the garbage to be classified is judged to be suspected mixed garbage; if the similarity between each sub-image and the local image information in the reference image information is greater than or equal to the second similarity threshold, the garbage to be classified is judged not to be suspected mixed garbage, and the garbage to be classified is directly stored in the corresponding category of the garbage bin with reference to the garbage classification type corresponding to the image information. The local image information in the reference image information in this application refers to searching for the part with the highest similarity with the sub-image information in the reference image information, comparing the part with the sub-image for similarity, and judging the similarity with the second similarity threshold. The relationship between the degree threshold; the contour line of the image to be classified is collected on the one hand to determine whether the garbage to be classified is mixed garbage based on the contour line later, and on the other hand because the contour line can more clearly distinguish the tray containing the garbage to be classified from the garbage to be classified; the purpose of dividing the first image is to more accurately determine the similarity with the reference image. When the garbage to be classified is mixed garbage, it is possible that the mixed garbage only accounts for a small part of the garbage to be classified. At this time, the entire first image is compared with the reference image. The accuracy of directly judging whether the garbage to be classified is mixed garbage is low. Therefore, the first image is divided and then compared. In this application, it is not limited to being divided into four equal parts, but can also be divided into five equal parts, six equal parts, seven equal parts, etc.; The comparing the first image with the second image comprises: The contour line of the garbage to be classified in the second image is extracted as the second contour line, and the length reference value P=|L2-L1| / L1 is calculated, where L1 is the length of the first contour line, and L2 is the length of the second contour line. If the length reference is greater than or equal to the length reference threshold, it is determined that the garbage to be classified is mixed garbage; If the length reference amount is less than the length reference amount threshold, the maximum inner diameter and the minimum inner diameter of the first contour line and the second contour line are extracted respectively, the maximum inner diameter and the minimum inner diameter of the first contour line divide the interior of the first contour line into four images to be compared within the first contour line, and the maximum inner diameter and the minimum inner diameter of the second contour line divide the interior of the second contour line into four comparison images within the second contour line. The maximum inner diameter and the minimum inner diameter in the present application refer to the distance between the longest two points and the distance between the shortest two points on the contour line of the garbage to be classified passing through the center point of the garbage to be classified, respectively. The reason why the first image and the second image are divided by the maximum inner diameter and the minimum inner diameter is that in the process of vibrating the garbage to be classified, the position, angle and orientation of the garbage to be classified may change. If the garbage to be classified is not mixed garbage, the position of its maximum inner diameter and the minimum inner diameter will not change. Therefore, the image is divided by the maximum inner diameter and the minimum inner diameter, so as to facilitate the comparison after the image is divided; If there is a certain comparison image whose similarity with the four images to be compared is less than the third similarity threshold, then it is determined that the garbage to be classified is mixed garbage.

[0024] Before collecting the overhead image of the garbage to be classified as the second image, the method further includes: The weight of the garbage to be classified after vibration is collected and compared with the weight of the garbage to be classified before vibration. If the difference between the weights of the garbage to be classified before and after vibration is greater than or equal to the weight difference threshold, the garbage to be classified is judged to be mixed garbage. Otherwise, the top view image of the garbage to be classified is collected as the second image. The weight of the garbage to be classified before vibration in the present application may refer to the weight of the garbage to be classified detected after the garbage to be classified senses the garbage. In the present embodiment, the garbage to be classified is held in a tray with fine holes, which facilitates the outflow of liquid when shaking to determine whether the garbage to be classified contains liquid.

[0025] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0026] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An automatic control system for garbage classification and processing, characterized in that: The automatic control system includes an identity collection module, a garbage sensing module, an image collection module, a first analysis module, a vibration module, a second analysis module and a garbage return control module. The identity collection module is used to collect and verify the identity information of the user, and after the user's identity information is verified, the garbage sensing module is turned on. When the garbage sensing module senses the garbage to be classified, the image collection module is ordered to collect the overhead image of the garbage to be classified at this time as a first image. The first analysis module analyzes the first image to determine whether the garbage to be classified is suspected mixed garbage. After the first analysis module determines that the garbage to be classified is suspected mixed garbage, the vibration module is ordered to vibrate the garbage to be classified, and after the vibration, the image collection module is ordered to collect the overhead image of the garbage to be classified at this time as a second image. The second analysis module compares the first image and the second image to determine whether the garbage to be classified is mixed garbage. The garbage return control module is used to control the garbage to be returned to the user when the garbage to be classified is determined to be mixed garbage.

2. The automatic control system for garbage classification processing according to claim 1 is characterized in that: The first analysis module includes a first similarity comparison module, a first contour extraction module, a sub-image division module and a second similarity comparison module. The first similarity comparison module compares the first image with an image in a preset garbage database, wherein the garbage database is used to pre-store image information of various garbage. In the garbage database, there is image information of a certain garbage whose similarity with the first image is greater than a first similarity threshold. The image information of the garbage is assumed to be reference image information. The first contour extraction module is used to extract the contour of the garbage to be classified in the first image as the first contour. The sub-image division module determines the positions of each quarter-divided point on the first contour according to the length of the first contour, connects the center point of the garbage to be classified with each quarter-divided point on the contour, and divides the garbage to be classified into four sub-images. The second similarity comparison module compares the four sub-images with the local image information in the reference image information respectively. If there is a sub-image whose similarity with the local image information in the reference image information is less than the second similarity threshold, the garbage to be classified is judged to be suspected mixed garbage.

3. The automatic control system for garbage classification processing according to claim 2 is characterized in that: The second analysis module includes a second contour extraction module, a length reference calculation module, a length reference comparison module, an inner diameter extraction module, a to-be-compared image acquisition module, a comparison image acquisition module and a third similarity comparison module. The second contour extraction module extracts the contour of the garbage to be classified in the second image as the second contour. The length reference calculation module calculates the length reference P=|L2-L1| / L1, where L1 is the length of the first contour and L2 is the length of the second contour. The length reference comparison module compares the length reference with a length reference threshold. If the length reference is greater than or equal to the length reference threshold, it is determined that the garbage to be classified is mixed garbage. If the length reference is greater than or equal to the length reference threshold, it is determined that the garbage to be classified is mixed garbage. When the value is less than the length reference threshold, the inner diameter extraction module extracts the maximum inner diameter and the minimum inner diameter of the first contour line and the second contour line respectively, the image to be compared acquisition module is used to obtain the four images to be compared that are divided within the first contour line by the maximum inner diameter and the minimum inner diameter of the first contour line, the comparison image acquisition module is used to obtain the four comparison images that are divided within the second contour line by the maximum inner diameter and the minimum inner diameter of the second contour line, the third similarity comparison module compares the comparison image with the image to be compared, and when there is a comparison image with the four images to be compared whose similarity is less than the third similarity threshold, it is determined that the garbage to be classified is mixed garbage.

4. The automatic control system for garbage classification processing according to claim 3 is characterized in that: The automatic control system also includes a weight acquisition module and a weight comparison module. The weight acquisition module is used to collect the weight of the garbage to be classified before and after vibration. The weight comparison module compares the weight of the garbage to be classified before and after vibration. When the difference in weight of the garbage to be classified before and after vibration is greater than or equal to a weight difference threshold, the garbage to be classified is judged to be mixed garbage. When the difference in weight of the garbage to be classified before and after vibration is less than the weight difference threshold, the image acquisition module is used to collect a top-view image of the garbage to be classified after vibration as the second image.

5. The automatic control system for garbage classification processing according to claim 1 is characterized in that: The automatic control system also includes an automatic control method, which includes the following steps: When the garbage sensor senses the garbage to be classified, a bird's-eye view image of the garbage to be classified is collected as a first image, and the first image is analyzed to determine whether the garbage to be classified is suspected mixed garbage. If the garbage to be classified is suspected to be mixed garbage, the garbage to be classified is vibrated and then a top view image of the garbage to be classified is collected as the second image. Compare the first image with the second image to determine whether the garbage to be classified is mixed garbage. If the garbage to be sorted is determined to be mixed garbage, the garbage to be sorted will be returned.

6. The automatic control system for garbage classification processing according to claim 5 is characterized in that: The analyzing the first image comprises: The first image is compared with an image in a preset garbage database, wherein the garbage database is used to pre-store image information of various garbage. If the similarity between the image information of a certain garbage in the garbage database and the first image is greater than a first similarity threshold, the image information of the garbage is set as the reference image information; Extracting the contour line of the garbage to be classified in the first image as the first contour line, determining the positions of each quarter point on the first contour line according to the length of the first contour line, connecting the center point of the garbage to be classified with each quarter point on the contour line respectively, and dividing the garbage to be classified into four sub-images; The four sub-images are compared with the local image information in the reference image information respectively. If the similarity between a certain sub-image and the local image information in the reference image information is less than a second similarity threshold, the garbage to be classified is determined to be suspected mixed garbage.

7. The automatic control system for garbage classification processing according to claim 6 is characterized in that: The comparing the first image with the second image comprises:. The contour line of the garbage to be classified in the second image is extracted as the second contour line, and the length reference value P=|L2-L1| / L1 is calculated, where L1 is the length of the first contour line, and L2 is the length of the second contour line. If the length reference is greater than or equal to the length reference threshold, it is determined that the garbage to be classified is mixed garbage; If the length reference is less than the length reference threshold, the maximum inner diameter and the minimum inner diameter of the first contour line and the second contour line are extracted respectively, the maximum inner diameter and the minimum inner diameter of the first contour line divide the interior of the first contour line into four images to be compared within the first contour line, and the maximum inner diameter and the minimum inner diameter of the second contour line divide the interior of the second contour line into four comparison images within the second contour line. If there is a certain comparison image whose similarity with the four images to be compared is less than the third similarity threshold, then it is determined that the garbage to be classified is mixed garbage.

8. The automatic control system for garbage classification processing according to claim 5 is characterized in that: Before collecting the overhead image of the garbage to be classified as the second image, the method further includes: The weight of the garbage to be sorted after vibration is collected, and compared with the weight of the garbage to be sorted before vibration. If the difference in weight before and after vibration of the garbage to be sorted is greater than or equal to a weight difference threshold, then the garbage to be sorted is judged to be mixed garbage. Otherwise, a top-view image of the garbage to be sorted is collected as the second image.

9. The automatic control system for garbage classification processing according to claim 5 is characterized in that: Before the garbage sensor senses the garbage to be classified, the method further includes: Collect the user's identity information and turn on the spam sensor when the user's identity verification is passed.

Images